Sentry error monitoring and performance tracing patterns for Next.js applications.

Designs comprehensive software solution architectures including system components, technology stacks, integration patterns, scalability strategies, and deployment models. Produces architecture...

Implement or extend a user-facing workflow in a web application, integrating with existing backend APIs. Use when the feature is primarily a UI/UX change backed by existing APIs, affects only the...

|

Manage Supabase projects, databases, migrations, Edge Functions, and storage using the `supabase` CLI.

The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with...

Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when...

Expert backend development guidance covering Node.js, Python, Java, Go, API design (REST/GraphQL/gRPC), database patterns, authentication, caching, message queues, microservices, and testing....

Provides comprehensive KeyCloak administration guidance including realm management, user/group administration, client configuration, authentication flows, identity brokering, authorization...

深度调研的多Agent编排工作流：把一个调研目标拆成可并行子目标，用 Claude Code 非交互模式（`claude -p`）运行子进程；联网与采集优先使用已安装的 skills，其次使用 MCP 工具；用脚本聚合子结果并分章精修，最终交付"成品报告文件路径 +...

Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor -...

Simplify and refine recently modified code for clarity and consistency. Use after writing code to improve readability without changing functionality.

Use when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task decomposition, progress tracking, and autonomous execution using Claude Code...

Designs comprehensive integration testing strategies including API testing, database testing, microservices testing, end-to-end testing, and test automation frameworks. Produces test plans, test...

智能软件著作权申请材料生成工具。自动分析项目源码，生成符合软著申请要求的软件说明书和源代码文档。支持关键词搜索、智能源码分析、格式化输出和PDF导出。

Provides comprehensive Oracle Cloud Infrastructure (OCI) guidance including compute instances, networking (VCN, load balancers, VPN), storage (block, object, file), database services (Autonomous...

Interact with a web browser. Can start a browser, connect to it, evaluate JavaScript, make screenshots, read console logs and let the user select DOM elements. Use when interacting with unknown...

Run knip to find and remove unused files, dependencies, and exports. Use for cleaning up dead code and unused dependencies.

Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than...